{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:W5TC3G7NR6ZXDUBILIOP6FAOYS","short_pith_number":"pith:W5TC3G7N","canonical_record":{"source":{"id":"2104.00436","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-01T12:40:07Z","cross_cats_sorted":[],"title_canon_sha256":"831791d120cb2c9b5a55e9f3fdb25ae454db22db3669cace6671f949f074880b","abstract_canon_sha256":"5c4c81c40436a72766934f586bbab3fc232390b18a8e9a1978cee8f8a844468e"},"schema_version":"1.0"},"canonical_sha256":"b7662d9bed8fb371d0285a1cff140ec48d486513da87e8e4bb34f4537e1c70f4","source":{"kind":"arxiv","id":"2104.00436","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00436","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00436v2","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00436","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"W5TC3G7NR6ZX","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"W5TC3G7NR6ZXDUBI","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"W5TC3G7N","created_at":"2026-07-05T05:03:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:W5TC3G7NR6ZXDUBILIOP6FAOYS","target":"record","payload":{"canonical_record":{"source":{"id":"2104.00436","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-01T12:40:07Z","cross_cats_sorted":[],"title_canon_sha256":"831791d120cb2c9b5a55e9f3fdb25ae454db22db3669cace6671f949f074880b","abstract_canon_sha256":"5c4c81c40436a72766934f586bbab3fc232390b18a8e9a1978cee8f8a844468e"},"schema_version":"1.0"},"canonical_sha256":"b7662d9bed8fb371d0285a1cff140ec48d486513da87e8e4bb34f4537e1c70f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:49.050181Z","signature_b64":"dhpCW4H8StIRoptcSzBebqON1Ku+rfgF8sRip79Xkv/QNdbE9gwj7gO4ZmwxvhFAlVJR/re+fa/lOj6W2QIdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7662d9bed8fb371d0285a1cff140ec48d486513da87e8e4bb34f4537e1c70f4","last_reissued_at":"2026-07-05T05:03:49.049779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:49.049779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.00436","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:03:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2p4aLoayRlavJ+l0MLslhVaikw/ic9b9ZS3UvPPqi4cINtOdyLtTo2BJZNJGm3Xl9xoMAotp9Mr0ZFIwGhrUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:39:51.168612Z"},"content_sha256":"25a4ee5322e9265cd4aa587291f6d75842c287828f18c008c14cf3f30c85f886","schema_version":"1.0","event_id":"sha256:25a4ee5322e9265cd4aa587291f6d75842c287828f18c008c14cf3f30c85f886"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:W5TC3G7NR6ZXDUBILIOP6FAOYS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Expressive Text-to-Speech using Style Tag","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Byoung Jin Choi, Jong Jin Kim, Minchan Kim, Nam Soo Kim, Sung Jun Cheon","submitted_at":"2021-04-01T12:40:07Z","abstract_excerpt":"As recent text-to-speech (TTS) systems have been rapidly improved in speech quality and generation speed, many researchers now focus on a more challenging issue: expressive TTS. To control speaking styles, existing expressive TTS models use categorical style index or reference speech as style input. In this work, we propose StyleTagging-TTS (ST-TTS), a novel expressive TTS model that utilizes a style tag written in natural language. Using a style-tagged TTS dataset and a pre-trained language model, we modeled the relationship between linguistic embedding and speaking style domain, which enable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00436","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.00436/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:03:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jfFvYwNONGbvwzV2XIaC8+pOk+oYVXCeLtdtKaheRqZx31nlG/PzbzpSfkjMfHo+vNGun8KL3GEHVxo++a6oCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:39:51.169142Z"},"content_sha256":"86a6434df74442d439dccf3a25ae8eda04e03f0fde4047ca1351220d98f7efde","schema_version":"1.0","event_id":"sha256:86a6434df74442d439dccf3a25ae8eda04e03f0fde4047ca1351220d98f7efde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS/bundle.json","state_url":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T02:39:51Z","links":{"resolver":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS","bundle":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS/bundle.json","state":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:W5TC3G7NR6ZXDUBILIOP6FAOYS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5c4c81c40436a72766934f586bbab3fc232390b18a8e9a1978cee8f8a844468e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-01T12:40:07Z","title_canon_sha256":"831791d120cb2c9b5a55e9f3fdb25ae454db22db3669cace6671f949f074880b"},"schema_version":"1.0","source":{"id":"2104.00436","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00436","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00436v2","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00436","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"W5TC3G7NR6ZX","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"W5TC3G7NR6ZXDUBI","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"W5TC3G7N","created_at":"2026-07-05T05:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:86a6434df74442d439dccf3a25ae8eda04e03f0fde4047ca1351220d98f7efde","target":"graph","created_at":"2026-07-05T05:03:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.00436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As recent text-to-speech (TTS) systems have been rapidly improved in speech quality and generation speed, many researchers now focus on a more challenging issue: expressive TTS. To control speaking styles, existing expressive TTS models use categorical style index or reference speech as style input. In this work, we propose StyleTagging-TTS (ST-TTS), a novel expressive TTS model that utilizes a style tag written in natural language. Using a style-tagged TTS dataset and a pre-trained language model, we modeled the relationship between linguistic embedding and speaking style domain, which enable","authors_text":"Byoung Jin Choi, Jong Jin Kim, Minchan Kim, Nam Soo Kim, Sung Jun Cheon","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-01T12:40:07Z","title":"Expressive Text-to-Speech using Style Tag"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00436","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:25a4ee5322e9265cd4aa587291f6d75842c287828f18c008c14cf3f30c85f886","target":"record","created_at":"2026-07-05T05:03:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5c4c81c40436a72766934f586bbab3fc232390b18a8e9a1978cee8f8a844468e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-01T12:40:07Z","title_canon_sha256":"831791d120cb2c9b5a55e9f3fdb25ae454db22db3669cace6671f949f074880b"},"schema_version":"1.0","source":{"id":"2104.00436","kind":"arxiv","version":2}},"canonical_sha256":"b7662d9bed8fb371d0285a1cff140ec48d486513da87e8e4bb34f4537e1c70f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7662d9bed8fb371d0285a1cff140ec48d486513da87e8e4bb34f4537e1c70f4","first_computed_at":"2026-07-05T05:03:49.049779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:49.049779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dhpCW4H8StIRoptcSzBebqON1Ku+rfgF8sRip79Xkv/QNdbE9gwj7gO4ZmwxvhFAlVJR/re+fa/lOj6W2QIdBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:49.050181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.00436","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25a4ee5322e9265cd4aa587291f6d75842c287828f18c008c14cf3f30c85f886","sha256:86a6434df74442d439dccf3a25ae8eda04e03f0fde4047ca1351220d98f7efde"],"state_sha256":"363a72fb479ed6c5294d7a464328ce0d3370bda5ae6ba0e29d2a6fe704f5d8db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xwfizV5OND3nxK6tu/DYS5X4toExRoBxIxJwva8GYou4o4oGixtLY52JUgi16/UJVJqcIgqHOzIQwGlCqB+TBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:39:51.174052Z","bundle_sha256":"6817d601f17edad076a0649703630d6c6f682fa043900e31bbe98e44dc4cb981"}}